Viet-Anh on Software Logo

What is: Adaptive Instance Normalization?

SourceArbitrary Style Transfer in Real-time with Adaptive Instance Normalization
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Adaptive Instance Normalization is a normalization method that aligns the mean and variance of the content features with those of the style features.

Instance Normalization normalizes the input to a single style specified by the affine parameters. Adaptive Instance Normaliation is an extension. In AdaIN, we receive a content input xx and a style input yy, and we simply align the channel-wise mean and variance of xx to match those of yy. Unlike Batch Normalization, Instance Normalization or Conditional Instance Normalization, AdaIN has no learnable affine parameters. Instead, it adaptively computes the affine parameters from the style input:

AdaIN(x,y)=σ(y)(xμ(x)σ(x))+μ(y)\textrm{AdaIN}(x, y)= \sigma(y)\left(\frac{x-\mu(x)}{\sigma(x)}\right)+\mu(y)